© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 13877
    Prev
    Next
    INDEX
    Explanations

    themes and concepts related to art, creativity, and personal expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words or phrases that express strong emotional intensity or dramatic significance.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    原始内容存档于
    -0.53
    fromnode
    -0.48
    enumii
    -0.43
     AssemblyCompany
    -0.43
     surla
    -0.41
    Selfer
    -0.39
    ㅐ
    -0.38
    WebElementEntity
    -0.37
     تضيفلها
    -0.37
    木坂
    -0.35
    POSITIVE LOGITS
     FTW
    0.94
     ftw
    0.91
    ?
    0.80
     galore
    0.73
     indeed
    0.68
    ?!?
    0.65
     huh
    0.64
    ?!
    0.63
     beware
    0.63
     ALERT
    0.62
    Activations Density 0.410%

    No Known Activations